Locomotion on Ant
882RewardPAWS (MLP)
Evaluation Results
| Method | Links | |
|---|---|---|
| PAWS (MLP)#Preferences=5002026.06 | 882 | |
| PAWS (Trans.)#Preferences=5002026.06 | 850 | |
| P-IQL#Preferences=5002026.06 | 847 | |
| Pref Trans.#Preferences=5002026.06 | 784 | |
| PAWS (MLP)#Preferences=502026.06 | 707 | |
| PAWS (Trans.)#Preferences=502026.06 | 685 | |
| IPL#Preferences=5002026.06 | 634 | |
| BC#Preferences=5002026.06 | 593 | |
| CPL+KL#Preferences=5002026.06 | 581 | |
| P-IQL#Preferences=502026.06 | 567 | |
| CPL#Preferences=5002026.06 | 563 | |
| BC#Preferences=502026.06 | 546 | |
| CPL+KL#Preferences=502026.06 | 518 | |
| CPL#Preferences=502026.06 | 508 | |
| Pref Trans.#Preferences=502026.06 | 505 | |
| IPL#Preferences=502026.06 | 384 |